my-university-labs / newfeelings Goto Github PK
View Code? Open in Web Editor NEWA smart album for Android which use tensorflow to classify images
A smart album for Android which use tensorflow to classify images
我在百度图片上收集了14种分类,每种类数量不同,最少有50左右,最多有900多张。根据作者你在博客上的步骤进行训练自己的数据集,但最后编译安装项目后相册页空白,没有完成分类过程。
在PC机上使用训练的pb文件能够准确识别,也已经经过处理,减小体积,并在config.java文件中做了如下修改:
` public static final int NUM_CLASSES = 14;
public static final int INPUT_SIZE = 299;
public static final int IMAGE_MEAN = 128;
public static final float IMAGE_STD = 128;
public static final String INPUT_NAME = "Mul";
public static final String OUTPUT_NAME = "final_result:0";
public static final String MODEL_FILE = "file:///android_asset/lala_graph.pb";
public static final String LABEL_FILE = "file:///android_asset/llll_labels.txt";
public static String[] album_type_name = {
"植物","艺术品",
"合影", "风景","演出",
"美食", "旅游","室内", "乐器", "自拍", "文字","建筑","聚餐","二次元"
};
public static String[] tf_type_name = {
"zhiwu","art",
"peoples", "view","show",
"food", "travel","indoor", "instration", "zipai", "word","establish","eat","er"
};`
其中我的labels文件如下:
indoor food travel word show zipai art zhiwu er establish peoples view instration eat
之所以是英文,是我之前使用中文分类,tensorflow无法构建.pb文件和labels文件,只有在使用英文字母的时候才可以正常训练。想问一下作者你是如何训练出中文标签的?希望作者看到有时间回复一下,这个问题困扰我好久了,谢谢!
in your blog,you say you just get the arm use tensorlfow dll,canyou share with me ,i do not know how to use bazel cross compile for arm.
我看了Tensorflow的介绍,感觉还有些不熟悉,我想下作者您是在windows 环境下集成的Android 项目吗?
我想是实现的 打开摄像头 ,画面出现的物体,会进行一个标注,标明这是什么,,,现在已经有.pb文件 在pc ,ios成功运行了,请问我该如何集成到android 呢?多谢
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.